Jack Halpern


   Data Licensing

Japanese Phonetic Database

The CJK Dictionary Institute (CJKI) is engaged in research on Chinese, Japanese and Korean (CJK) phonetics and phonology and the development of phonetic/phonological databases referred to as the Japanese Phonetic Database (JPD). The JPD provides IPA phonetic transcriptions that accurately indicate how Japanese names and words are pronounced in actual speech, as well as accent codes, for each entry.

After years of development work, in December 2007 CJKI announced the completion of the first phase of the project by delivering JPD to The National Language Research Institute, the largest and most respected government organization in Japan that conducts scientific research on the Japanese language. To our knowledge, this is the first database of its kind which provides both IPA and accent codes covering Japanese vocabulary.

Developed by a team of experienced Japanese editors, this database can be used for such applications as:

  • Speech synthesis systems (text-to-speech generation or TTS).
  • Pedagogical research to help in the acquisition of Japanese as a foreign language.
  • Research and development of Japanese speech technology in general.


Each entry is accompanied by various attributes, such as:

  • Rich phonological information, such as phonemic and phonetic transcriptions and accent codes.
  • Grammatical information such as part-of-speech codes.
  • Semantic classification codes such as the TYPE of proper noun.

Editorial Policy

The JDP was compiled to meet the needs of speech technology requirements, especially the generation of natural speech (TTS), by experienced editors with in-depth knowledge of Japanese phonology and phonetics. The phonetic transcriptions can be provided in various formats other than IPA, at different levels of precision, and fine-tuned to the needs of specific applications. To properly understand the data samples and field descriptions below, it is necessary to refer to The Challenges of Japanese Speech Technology, which describes the linguistic details.

Description of Fields

Field Description
Headword Orthographic representation of Japanese word (kana/kanji)
POS Part-of-speech code (other grammatical/morphological attributes available) (see Japanese Lexical Database.)
Type A subclassification that identifies the semantic properties of the headword or gives supplementary information such as grammatical attributes, especially for proper nouns. See cpostype.htm for TYPE code definitions.
Accent This shows the pitch accent for the standard Tokyo Dialect, compiled by experienced native linguists. Since pitch accent for names is not standardized (it could vary with the individual), the concept of "100% accuracy" does not apply to names. Sometimes, multiple accents for the same name may be given. The number in the Accent field represents the accented mora – that is, the point after which the accent begins to fall. For example, "1" means that the first mora is accented or high pitched, and that the pitch falls starting from the second mora. Accentless words are represented by “0”.
Kana Reading The reading of the headword in katakana.
Kana Phonemic This field disambiguates the kana ambiguities in the Kana Reading field, and serves as a phonemic representation. Though it does contain minimal phonetic information, such as /g/ nasalization and devoicing, it does not accurately indicate allophonic variants, which is the function of the Phonetic field.
  • [‘] Follows the accented mora, marking the point from which the pitch begins to fall.
  • [&] The preceding /g/ is optionally nasalized, becoming [ŋ], a phonetically distinct allophone of [g], e.g. "アオカゲ&" represents [aokaŋe].
  • [^] The preceding vowel is devoiced. This is common for /i/ and /u/ between voiceless consonants, such as in "アイノス^ケ", where "ス^" represents [sɯ̥], not [sɯ].
  • [~] The preceding vowel is elongated. For example, "ウンドウ~ " (運動) represents /undoo/ [ɯndoː], whereas "イノウエ" (井上) represents /inoue/ [inoɯe], not /inooe/ [inoːe].
Phonemic This field fully disambiguates the kana ambiguities in the Kana Reading field, and thus serves as a precise phonemic representation. It does not indicate allophonic variants, which is the function of the Phonetic field.
Phonetic The phonemic transcription in the Phonemic field is insufficient for accurate voice synthesis, whose goal is naturally-sounding Japanese. This field, the most important feature of this database, provides what can be roughly considered a broad phonetic transcription in IPA (International Phonetic Alphabet). In practice, it is considerably more accurate than traditional broad transcriptions, and accurately reflects allophonic variations fairly close to actual pronunciation (narrow transcriptions, not necessarily desirable, could be made available.)
Remarks Comments on phonetic/phonological processes.
Rank Rank based on the occurrence of frequency in corpora and lexical sources can be provided (not shown here).

Data Sample

The most important features are the IPA transcription in the "Phonetic" field, which provides a precise representation of many allophonic changes such as devoicing and nasalization, and the "Accent" field, which gives the accent pattern code. Though allophonic variations occur mostly unconsciously in native speaker speech, they have a marked effect on the naturalness of synthesized speech.

POS TYPE Accent Kana Reading Kana Phonemic Phonemic Phonetic Remarks
NC - 3 カガミ カガ&ミ kagami kaŋami voiced velar nasal
NC - 3 カガミ カガミ kagami kaɡami voiced velar stop
NC - 3 カガミ カガ&ミ kagami kaɣami voiced velar fricative
危ない AJ - 0 アブナイ アブナイ abunai abɯnai voiced bilabial plosive
危ない AJ - 0 アブナイ アブナイ abunai aβɯ̥nai voiced bilabial fricative
飾り NC - 0 カザリ カザリ kazari kazaɾi voiced alveolopalatal fricative
ザリガニ NC - 0 ザリガニ ザリガ&ニ zarigani dzaɾiɡaɲi alveolopalatal affricate, palatal nasal
新聞 NC - 0 シンブン シンブン siNbuN ɕimbɯɴ  
自分 NC - 0 ジブン ジブン zibuN dʑibɯɴ weakening of voiced alveolopalatal plosive (fricativized)
比較 VN - 0 ヒカク ヒ^カク hikaku hi̥kakɯ devoicing of [hi]
比較 VN - 0 ヒカク ヒカク hikaku hikakɯ no devoiced vowel
続く V5 - 0 ツヅク ツ^ヅク tuzuku tsɯ̥zɯkɯ devoicing of [tsɯ]
続く V5 - 0 ツヅク ツヅク tuzuku tsɯzɯkɯ no devoiced vowel
NC - 2 ハジ ハジ hazi haʑi voiced alveolopalatal fricative
NC - 2 ハジ ハジ hazi hadʑi voiced alveolopalatal affricate
NC - 0 ハチ ハチ hati hatɕi  
NC - 2 ハチ ハチ hati hatɕi  
NC - 1 u ʔɯʔ glottal stop
アッ I - 1 アッ アッ aQ glottal stop
運動 VN - 0 ウンドウ ウンドウ~ uNdoo ɯndoː  
病院 NC - 0 ビョウイン ビョウ~イン bjooiN bʲoːiɴ voiced palatal
美容院 NC - 2 ビヨウイン ビヨ'ウ~イン bijooiN bijoːiɴ  
宴会 NC - 0 エンカイ エンカイ eNkai eŋkai  
蒟蒻 NC - 0 コンニャク コンニャク koNnjaku koɲɲakɯ alveolar nasal, voiced palatal nasal
NC - 1 ホン ホ'ン hoN hoɴ uvular nasalized consonant
NC - 1 ホン ホ'ン hoN hõ close front nasalized vowel
本案 NC - 1 ホンアン ホ'ンアン hoNaN hoãɴ close back nasalized vowel (slight nasalization before /N/)
本意 NC - 1 ホンイ ホ'ンイ hoNi hõĩ close front nasalized vowel
本会議 NC - 3 ホンカイギ ホンカイギ hoNkaigi hoŋkaiŋi velar nasal
本棚 NC - 1 ホンダナ ホ'ンダナ hoNdana hondana alveolar nasal
本箱 NC - 1 ホンバコ ホ'ンバコ hoNbako hombako bilabial nasal
電話 NC - 0 デンワ デンワ deNwa deẽwa  
案外 D - 1 アンガイ ア'ンガ&イ aNgai aŋŋai voiced velar nasal
案外 D - 1 アンガイ ア'ンガイ aNgai aŋɡai voiced velar stop
NC - 2 タニ タニ tani taɲi voiced palatal nasal
単位 NC - 1 タンイ タ'ンイ taNi taĩ  
NC - 0 イカリ イカリ ikari ikaɾi  
怒り NC - 3 イカリ イカリ ikari ikaɾi  
休み NC - 3 ヤスミ ヤスミ jasumi jasɯmi  
これから NC - 4 コレカラ コレカラ korekara koɾekaɾa  
無銭飲食 NC - 4 ムセンインショク ムセンインショク^ museNiNsjoku mɯseĩɕ̃oku̥ [ku]の無声化
井口 NP S 1 イグチ イ'グ&チ iguti iŋɯtɕi  
磯貝 NP S 2 イソガイ イソ'ガ&イ isogai isoŋai  
伊藤 NP S 0 イトウ イトウ~ itoo itoː  
稲垣 NP S 2 イナガキ イナ'ガ&キ inagaki inaŋaki  
稲田 NP S 0 イナダ イナダ inada inada  
井上 NP S 0 イノウエ イノウエ inoue inoɯe "ノウ" is pronounced to [oɯ], not long vowel
栄次郎 NP M 1 エイジロウ エ'イ~ジロウ~ eiziroo eːʑiɾoː voiced alveolopalatal fricative
岸和田 NP PS 0 キシワダ キ^シワダ kisiwada ki̥ɕiwada devoicing of [ki]
銀座 NP P 0 ギンザ ギンザ giNza ɡindza voiced alveolopalatal affricate
慎一 NP M 0 シンイチ シンイチ siNiti ɕiĩtɕi vowel nasalization of /N/
純子 NP F 1 ジュンコ ジュ'ンコ zjuNko dʑɯŋko weakening of voiced alveolopalatal plosive(fricativized)
関口 NP S 2 セキグチ セキ'グ&チ sekiguti sekiŋɯtɕi  
大地 NP M 1 ダイチ ダ'イチ daiti daitɕi̥ devoicing of [tɕi]
東京 NP P 0 トウキョウ トウ~キョウ~ tookjoo toːkʲoː devoiced palatal
福生 NP P 0 フッサ フッサ huQsa ɸɯ̥s̚sa first [s] is unreleased, devoicing of [ɸɯ]
一本 NC - 1 イッポン イッポン iQpoN ip̚poɴ first [p] is unreleased
丸井 NP S 0 マルイ マルイ marui maɾɯi